EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Benchmarking Time-Series Artificial Intelligence Architectures for Wearable Sensor-Based Fall Prediction: A Synthetic Data Simulation Framework

Edward R Sykes iD, Mohammad Maghsoudimehrabani iD, Abdulrahman Al-Shanoon iD

Sensors · 24.05.2026 · 26 (11) · 3326

DOI: 10.3390/s26113326 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 24.05.2026. Verfasst von Edward R Sykes und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, University of Guelph, Guelph, ON N1G 2W1, Canada. Hauptthemen laut MEDLINE: Accidental Falls, Artificial Intelligence, Prediction Algorithms, Wearable Electronic Devices. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Natural Sciences and Engineering Research Council of Canada, Natural Sciences and Engineering Research Council of Canada.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Falls among older adults are a major cause of injury and loss of independence, yet most existing systems detect falls only after onset or provide very limited warning time. This study presents a synthetic benchmarking framework for early fall-risk prediction using multimodal wearable-inspired time-series data and compares classical and temporal machine learning architectures under a realistic evaluation protocol. A synthetic dataset of 1000 sequences was generated to emulate normal activity, slip events, and pre-fall instability using biomechanical, physiological, and contextual variables. Eight baseline models and two augmented temporal variants were trained and evaluated using subject-wise splits to reduce leakage. Performance differed substantially by model family and evaluation protocol. Classical baselines achieved the strongest overall macro-F1 scores, whereas temporal models showed more modest discrimination. Under a fixed alerting rule, operational early-warning behavior varied considerably: some models failed to trigger alerts, while others achieved higher pre-fall trigger rates at the cost of increased false alarms. These findings show that apparent performance depends strongly on partitioning strategy, calibration, and alert design. The proposed framework provides a reproducible basis for benchmarking early-warning fall-risk models and supports future validation using real-world cohorts and deployment-oriented calibration strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Accidental FallsArtificial IntelligencePrediction AlgorithmsWearable Electronic DevicesHumansBenchmarkingComputer SimulationMachine Learning

Stichwörter der Autor:innen

early warningfall predictionmulti-sensor fusionolder adultssynthetic data simulationtemporal deep learningtime-series classificationwearable sensors

Autor:innen und Institutionen

  • School of Computer Science, University of Guelph, Guelph, ON N1G 2W1, Canada.

ORCID-Profile: Edward R Sykes, Mohammad Maghsoudimehrabani, Abdulrahman Al-Shanoon

Förderung

  • The Natural Sciences and Engineering Research Council of Canada
  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Sykes, E. R., Maghsoudimehrabani, M., & Al-Shanoon, A. (2026). Benchmarking Time-Series Artificial Intelligence Architectures for Wearable Sensor-Based Fall Prediction: A Synthetic Data Simulation Framework. Sensors, 26(11), 3326. https://doi.org/10.3390/s26113326

Vancouver

Sykes ER, Maghsoudimehrabani M, Al-Shanoon A. Benchmarking Time-Series Artificial Intelligence Architectures for Wearable Sensor-Based Fall Prediction: A Synthetic Data Simulation Framework. Sensors. 2026;26(11):3326. doi:10.3390/s26113326

BibTeX
@article{Sykes2026,
  author = {Sykes, Edward R and Maghsoudimehrabani, Mohammad and Al-Shanoon, Abdulrahman},
  title = {Benchmarking Time-Series Artificial Intelligence Architectures for Wearable Sensor-Based Fall Prediction: A Synthetic Data Simulation Framework},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3326},
  doi = {10.3390/s26113326}
}
Kostenlos starten →